Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already covers the safety profile, but the description adds real behavioral context beyond annotations: identical failures are grouped by error fingerprint for runs/workflows, job/attempt targets yield a focused diagnosis with evidence, and the result is empty when no failure evidence exists. That empty-result disclosure is genuinely useful for agent decision-making.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with purpose and containing no filler; the routing hint is placed last where it lands well. The trailing 'Depot: CIService/GetFailureDiagnosis.' identifier adds little for an agent, a minor tax on an otherwise efficient description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so qualitatively — describing grouped fingerprints, focused evidence, and the empty case. It could say more about the shape or size of the diagnosis, but nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning by explaining how behavior differs per target_type (grouped vs. focused diagnosis), which helps an agent choose between run, workflow, job and attempt. It stops short of clarifying the id format for each target type.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get Depot's failure diagnosis for a CI run, workflow, job or attempt') and enumerates the exact target types. It also distinguishes itself from log/status siblings by describing what the diagnosis actually contains (fingerprint grouping vs. focused evidence).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly declares 'The best first call when a run failed', giving a clear triggering condition. It does not name competing alternatives (e.g. get_job_logs) or state exclusions, so it falls short of a full when/when-not routing statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.